Advances in Active Appearance Models

Abstract

This paper presents advances in the construction and use of Active Appearance Models (AAMs) for image interpretation. AAMs are photo-realistic generative models of object appearance that can be used to rapidly locate deformable objects in images. We extend the AAM method to include coloured texture and present an enhanced search algorithm with the ability to locate partially occluded objects. Previously, AAMs have been limited by the need for good manual initialisation. In this paper, we describe a hierarchical search algorithm that overcomes this drawback. The extended AAM method provides a complete, unified scheme for model based image interpretation. We demonstrate the application of the scheme to the task of locating faces in images.

Cite

Text

Edwards et al. "Advances in Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.791209

Markdown

[Edwards et al. "Advances in Active Appearance Models." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/edwards1999iccv-advances/) doi:10.1109/ICCV.1999.791209

BibTeX

@inproceedings{edwards1999iccv-advances,
  title     = {{Advances in Active Appearance Models}},
  author    = {Edwards, Gareth J. and Cootes, Timothy F. and Taylor, Christopher J.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {137-142},
  doi       = {10.1109/ICCV.1999.791209},
  url       = {https://mlanthology.org/iccv/1999/edwards1999iccv-advances/}
}